Dental caries classification using depthwise separable convolutional neural network for teledentistry system

Caries may be halted or reversed in their progression by early detection, better hygiene habits, and coadministered drugs. The major clinical procedures for identifying dental caries are visual-tactile examination radiography. However, due to location, approximate exceedingly difficult detect affect the assessment. Incorrect interpretations also hinder diagnostic procedure. Computational approaches technology can used help dentists assess caries. Teledentistry has ability improve health care providing access services from a remote location. helps various stages of lesions using neural network devices connected internet. This research develops an image classification teledentistry systems depthwise separable convolutional network. trainable parameters reduction convolution (DSC) successfully reduces computational cost conventional networks (CNN). As result, DSC model is reduced 91.49% when compared traditional CNN model. Several models accuracies training, validation, evaluation, testing stages.